Macro-Driven Rotation Between Effective and Style Factors

Summary

This report proposes treating effective factors and style factors differently when allocating across a multi-factor equity strategy. Effective factors rotate according to their relative strength, which the report seeks to explain using macroeconomic variables, market variables, and calendar effects. Style factors, by contrast, are rotated directly according to market style. The analysis finds that traditional factor momentum or reversal does not explain effective-factor rotation well, while explanatory variables may better account for relative rankings among factors than for the returns of individual factors.

The report compares rolling stepwise linear regression on factor returns with ordinal regression on factor rankings. Against an equal-weight factor portfolio reporting a 9.50% long-term return, it reports 12.16% for stepwise regression and 12.76% for ordinal regression. Stepwise regression has lower reported volatility, while ordinal regression has a smaller maximum drawdown and more stable weights, which the report argues could reduce turnover and trading costs. Results rely on the report’s sample and modeling assumptions; the excerpt does not specify enough about implementation or validation to establish robustness, and its idealized discussion assumes factor returns are known when considering potential gains.

Key ideas

• The report separates effective-factor rotation from style-factor rotation because it sees their drivers as different.
• Macro, market, and calendar variables are used to explain relative factor strength.
• Stepwise regression models factor returns, while ordinal regression models factor rankings.
• Both rolling approaches are reported to outperform equal factor weighting in the study.
• Ordinal regression has more stable weights in the reported comparison, while stepwise regression has lower volatility.

Tags

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.